做网站用什么做,宁波网站制作网站,甘肃建设网站,网站维护明细报价表在本文中我们将探讨使用开源大型语言多模态模型(Large Language Multi-Modal)构建检索增强生成(RAG)系统。本文的重点是在不依赖LangChain或LLlama index的情况下实现这一目标#xff0c;这样可以避免更多的框架依赖。
什么是RAG
在人工智能领域#xff0c;检索增强生成(re…在本文中我们将探讨使用开源大型语言多模态模型(Large Language Multi-Modal)构建检索增强生成(RAG)系统。本文的重点是在不依赖LangChain或LLlama index的情况下实现这一目标这样可以避免更多的框架依赖。
什么是RAG
在人工智能领域检索增强生成(retrieve - augmented Generation, RAG)作为一种变革性技术改进了大型语言模型(Large Language Models)的能力。从本质上讲RAG通过允许模型从外部源动态检索实时信息来增强AI响应的特异性。
该体系结构将生成能力与动态检索过程无缝结合使人工智能能够适应不同领域中不断变化的信息。与微调和再训练不同RAG提供了一种经济高效的解决方案允许人工智能在不改变整个模型的情况下能够得到最新和相关的信息。
RAG的作用
1、提高准确性和可靠性:
通过将大型语言模型(llm)重定向到权威的知识来源来解决它们的不可预测性。降低了提供虚假或过时信息的风险确保更准确和可靠的反应。
2、增加透明度和信任:
像LLM这样的生成式人工智能模型往往缺乏透明度这使得人们很难相信它们的输出。RAG通过允许组织对生成的文本输出有更大的控制解决了对偏差、可靠性和遵从性的关注。
3、减轻幻觉:
LLM容易产生幻觉反应——连贯但不准确或捏造的信息。RAG通过确保响应以权威来源为基础减少关键部门误导性建议的风险。
4、具有成本效益的适应性:
RAG提供了一种经济有效的方法来提高AI输出而不需要广泛的再训练/微调。可以通过根据需要动态获取特定细节来保持最新和相关的信息确保人工智能对不断变化的信息的适应性。
多模式模态模型
多模态涉及有多个输入并将其结合成单个输出以CLIP为例CLIP的训练数据是文本-图像对通过对比学习模型能够学习到文本-图像对的匹配关系。
该模型为表示相同事物的不同输入生成相同(非常相似)的嵌入向量。 多模
态大型语言(multi-modal large language)
GPT4v和Gemini vision就是探索集成了各种数据类型(包括图像、文本、语言、音频等)的多模态语言模型(MLLM)。虽然像GPT-3、BERT和RoBERTa这样的大型语言模型(llm)在基于文本的任务中表现出色但它们在理解和处理其他数据类型方面面临挑战。为了解决这一限制多模态模型结合了不同的模态从而能够更全面地理解不同的数据。
多模态大语言模型它超越了传统的基于文本的方法。以GPT-4为例这些模型可以无缝地处理各种数据类型包括图像和文本从而更全面地理解信息。
与RAG相结合
这里我们将使用Clip嵌入图像和文本将这些嵌入存储在ChromDB矢量数据库中。然后将利用大模型根据检索到的信息参与用户聊天会话。 我们将使用来自Kaggle的图片和维基百科的信息来创建一个花卉专家聊天机器人
首先我们安装软件包 ! pip install -q timm einops wikipedia chromadb open_clip_torch!pip install -q transformers4.36.0!pip install -q bitsandbytes0.41.3 accelerate0.25.0预处理数据的步骤很简单只是把图像和文本放在一个文件夹里 可以随意使用任何矢量数据库这里我们使用ChromaDB。 import chromadbfrom chromadb.utils.embedding_functions import OpenCLIPEmbeddingFunctionfrom chromadb.utils.data_loaders import ImageLoaderfrom chromadb.config import Settingsclient chromadb.PersistentClient(pathDB)embedding_function OpenCLIPEmbeddingFunction()image_loader ImageLoader() # must be if you reads from URIsChromaDB需要自定义嵌入函数 from chromadb import Documents, EmbeddingFunction, Embeddingsclass MyEmbeddingFunction(EmbeddingFunction):def __call__(self, input: Documents) - Embeddings:# embed the documents somehow or imagesreturn embeddings这里将创建2个集合一个用于文本另一个用于图像 collection_images client.create_collection(namemultimodal_collection_images, embedding_functionembedding_function, data_loaderimage_loader)collection_text client.create_collection(namemultimodal_collection_text, embedding_functionembedding_function, )# Get the ImagesIMAGE_FOLDER /kaggle/working/all_dataimage_uris sorted([os.path.join(IMAGE_FOLDER, image_name) for image_name in os.listdir(IMAGE_FOLDER) if not image_name.endswith(.txt)])ids [str(i) for i in range(len(image_uris))]collection_images.add(idsids, urisimage_uris) #now we have the images collection对于Clip我们可以像这样使用文本检索图像 from matplotlib import pyplot as pltretrieved collection_images.query(query_texts[tulip], include[data], n_results3)for img in retrieved[data][0]:plt.imshow(img)plt.axis(off)plt.show()也可以使用图像检索相关的图像 文本集合如下所示 # now the text DBfrom chromadb.utils import embedding_functionsdefault_ef embedding_functions.DefaultEmbeddingFunction()text_pth sorted([os.path.join(IMAGE_FOLDER, image_name) for image_name in os.listdir(IMAGE_FOLDER) if image_name.endswith(.txt)])list_of_text []for text in text_pth:with open(text, r) as f:text f.read()list_of_text.append(text)ids_txt_list [idstr(i) for i in range(len(list_of_text))]ids_txt_listcollection_text.add(documents list_of_text,ids ids_txt_list)然后使用上面的文本集合获取嵌入 results collection_text.query(query_texts[What is the bellflower?],n_results1)results结果如下 {ids: [[id0]],distances: [[0.6072186183744086]],metadatas: [[None]],embeddings: None,documents: [[Campanula () is the type genus of the Campanulaceae family of flowering plants. Campanula are commonly known as bellflowers and take both their common and scientific names from the bell-shaped flowers—campanula is Latin for little bell.\nThe genus includes over 500 species and several subspecies, distributed across the temperate and subtropical regions of the Northern Hemisphere, with centers of diversity in the Mediterranean region, Balkans, Caucasus and mountains of western Asia. The range also extends into mountains in tropical regions of Asia and Africa.\nThe species include annual, biennial and perennial plants, and vary in habit from dwarf arctic and alpine species under 5 cm high, to large temperate grassland and woodland species growing to 2 metres (6 ft 7 in) tall.]],uris: None,data: None}或使用图片获取文本 query_image /kaggle/input/flowers/flowers/rose/00f6e89a2f949f8165d5222955a5a37d.jpgraw_image Image.open(query_image)doc collection_text.query(query_embeddingsembedding_function(query_image),n_results1,)[documents][0][0]上图的结果如下 A rose is either a woody perennial flowering plant of the genus Rosa (), in the family Rosaceae (), or the flower it bears. There are over three hundred species and tens of thousands of cultivars. They form a group of plants that can be erect shrubs, climbing, or trailing, with stems that are often armed with sharp prickles. Their flowers vary in size and shape and are usually large and showy, in colours ranging from white through yellows and reds. Most species are native to Asia, with smaller numbers native to Europe, North America, and northwestern Africa. Species, cultivars and hybrids are all widely grown for their beauty and often are fragrant. Roses have acquired cultural significance in many societies. Rose plants range in size from compact, miniature roses, to climbers that can reach seven meters in height. Different species hybridize easily, and this has been used in the development of the wide range of garden roses.这样我们就完成了文本和图像的匹配工作其实这里都是CLIP的工作下面我们开始加入LLM。 from huggingface_hub import hf_hub_downloadhf_hub_download(repo_idvisheratin/LLaVA-3b, filenameconfiguration_llava.py, local_dir./, force_downloadTrue)hf_hub_download(repo_idvisheratin/LLaVA-3b, filenameconfiguration_phi.py, local_dir./, force_downloadTrue)hf_hub_download(repo_idvisheratin/LLaVA-3b, filenamemodeling_llava.py, local_dir./, force_downloadTrue)hf_hub_download(repo_idvisheratin/LLaVA-3b, filenamemodeling_phi.py, local_dir./, force_downloadTrue)hf_hub_download(repo_idvisheratin/LLaVA-3b, filenameprocessing_llava.py, local_dir./, force_downloadTrue)我们是用visheratin/LLaVA-3b from modeling_llava import LlavaForConditionalGenerationimport torchmodel LlavaForConditionalGeneration.from_pretrained(visheratin/LLaVA-3b)model model.to(cuda)加载tokenizer from transformers import AutoTokenizertokenizer AutoTokenizer.from_pretrained(visheratin/LLaVA-3b)然后定义处理器方便我们以后调用 from processing_llava import LlavaProcessor, OpenCLIPImageProcessorimage_processor OpenCLIPImageProcessor(model.config.preprocess_config)processor LlavaProcessor(image_processor, tokenizer)下面就可以直接使用了 question Answer with organized answers: What type of rose is in the picture? Mention some of its characteristics and how to take care of it ?query_image /kaggle/input/flowers/flowers/rose/00f6e89a2f949f8165d5222955a5a37d.jpgraw_image Image.open(query_image)doc collection_text.query(query_embeddingsembedding_function(query_image),n_results1,)[documents][0][0]plt.imshow(raw_image)plt.show()imgs collection_images.query(query_urisquery_image, include[data], n_results3)for img in imgs[data][0][1:]:plt.imshow(img)plt.axis(off)plt.show()得到的结果如下 结果还包含了我们需要的大部分信息 这样我们整合就完成了最后就是创建聊天模板 prompt |im_start|systemA chat between a curious human and an artificial intelligence assistant.The assistant is an exprt in flowers , and gives helpful, detailed, and polite answers to the humans questions.The assistant does not hallucinate and pays very close attention to the details.|im_end||im_start|userimage{question} Use the following article as an answer source. Do not write outside its scope unless you find your answer better {article} if you thin your answer is better add it after document.|im_end||im_start|assistant.format(questionquestion, articledoc)如何创建聊天过程我们这里就不详细介绍了完整代码在这里
https://avoid.overfit.cn/post/c2d8059cc5c145a48acb5ecb8890dc0e
作者Ahmed Haytham
